Insights for AI builders
Tutorials, product updates, and ideas to help you build and ship AI applications faster.
Subscribe via RSS
The Subtraction Principle: Why Removing Agent Tools Often Improves Performance
Research shows adding more tools to AI agents can hurt results. Learn the subtraction principle and how to audit your agent harness for better outputs.
Time Horizons Benchmark Numbers Are Understated by ~35% — Here's the Statistical Reason Why
Using a fixed-slope logistic fit — arguably more valid — pushes the published Time Horizons numbers up 35%. The co-author explains the methodology gap.
What Is Claude MCP? How Anthropic's Connectors Work with Blender, Adobe, and More
Claude's MCP connectors let AI issue commands directly to creative apps like Blender and Adobe. Learn how they work and what they can actually do.
What Is Harness Engineering? Why Your Agent's Wrapper Matters More Than the Model
Stanford research shows the same model can perform 6x better depending on its harness. Learn what harness engineering is and why it changes everything.
xAI Grok Voice API Is Live: 4 New Voice and Video Synthesis Capabilities Released This Week
xAI's voice cloning API is live without an enterprise plan. Plus Lucy 2.1 virtual try-on at $0.02/second. Here's what's new and what it costs.
xAI Grok Voice Clone vs. Google Voice Model — Which Is More Convincing in 2026?
xAI's clone fooled thousands of listeners at near 50/50. Google's model is 'very instructable.' Here's how the two voice synthesis approaches compare.
Agent Burnout Hits at Hour 4 — Not Hour 8: Why AI-Assisted Work Drains Differently Than Normal Work
Agent work burns through judgment and context-switching, not typing. Why you hit a wall at 4 hours and what to do about it.
AI Agents Don't Save Time — They Create an Infinite Backlog: 5 New Organizational Roles Emerging Right Now
Agents expose everything you could be doing, not just what you are doing. Five new roles — from context librarian to eval engineer — are emerging.
AI Benchmarks Are Broken: 5 Methodological Flaws in Time Horizon Metrics You Need to Understand
A fixed-slope fix alone would push Meter's numbers up 35%. Five structural problems with how AI capability benchmarks are built and reported.
Run the 4-Bucket AI Job Audit in 20 Minutes: Which Parts of Your Work Are Already on Thin Ice?
Theater, Commodity, On-the-Line, Durable. Audit the last two weeks of your work and find out what AI can already replace before your boss does.
Anthropic's Economic Index Shows 49% of Jobs Already Have 25%+ of Tasks Done by Claude — Is Yours One of Them?
Nearly half of all jobs have already handed a quarter of their tasks to Claude. Here's how to find out where your role stands.
Automate Weekly Ad Generation with Claude Code: 4 Skill Files and Routines That Run Without You
Skill files as reusable prompt recipes plus Claude Code routines on a cron schedule — here's how to build a self-running creative pipeline.
Beth Barnes on Meter's Time Horizons: The Error Bars Are 2x — Here's What the Benchmark Actually Tells You
Meter's co-founder admits error bars are 2x in either direction. Here's the honest breakdown of what time horizon benchmarks can and can't tell you.
Box's CEO Is Hiring 'Agent Engineers' — The New Role That Runs AI Across Every Business System
Aaron Levy is creating internal FTE roles to wire AI agents across Salesforce, Workday, and Box. Here's what the job actually requires.
How to Build and A/B Test a High-Converting Landing Page with Claude Code for Free (PostHog + Vercel Stack)
PostHog for A/B testing, Vercel for hosting, Claude Code to build it — the entire CRO stack costs $0. Step-by-step setup guide.
How to Build an Entire Brand's Ad Creative with Claude Code and Higgsfield in Under 5 Minutes
One prompt. Five minutes. A full headphone brand with product photos, Instagram ads, and UGC videos. Here's the exact workflow.
How to Build a Brand Identity File for Claude Code: The AI Interview Method
Instead of writing your identity file from scratch, let Claude interview you. Here's how to create user.md, soul.md, and brand context files in minutes.
Build a Voice Agent That Books Appointments in Under 1 Hour Using Claude Code and ElevenLabs
No API docs required. Claude Code reads the ElevenLabs docs, configures the agent, adds Cal.com booking tools, and embeds the widget for you.
How to Build a Voice Agent with Claude Code and ElevenLabs in 15 Minutes
Build a fully functional voice agent using Claude Code and ElevenLabs that books calendar appointments and answers questions from your website.
Claude Code Found a UTC Timezone Bug by Reading Conversation Transcripts — No API Logs Required
Claude Code read turn 16 of a voice agent transcript and identified a Cal.com UTC bug the developer never spotted. Here's how it works.
How to Use Claude Routines to Schedule Autonomous AI Workflows
Claude Routines let you schedule AI tasks to run automatically on a cadence. Learn how to set them up for content generation, research, and more.
ClaudeMem vs. Dumping Full Context into Claude Code: The 10x Token Cost Difference Explained
Dumping all past context into Claude Code is expensive. ClaudeMem's three-layer vector search cuts retrieval token costs by ~10x.
Cloudflare Moves Post-Quantum Deadline to 2029: 5 Things Every Security Team Needs to Know Now
Cloudflare called the new quantum research 'a real shock' and pulled its deadline forward. Here's what changed and what to do.
Context Mode for Claude Code Compresses 315KB Sessions to 5KB — Here's How to Install and Use It
Context Mode achieves a 63x compression ratio on Claude Code sessions. Install steps, slash commands, and when to use it over alternatives.